Character Arrangement Interpretation for Complex Document Layouts

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current technologies for processing images of printed documents with complex character arrangements often require manual editing and data entry due to limitations in optical character recognition (OCR), leading to inefficiencies and errors.

Innovation Solution

A system and method for interpreting character arrangements in images, which captures and processes images to generate a data structure, such as a table or spreadsheet, by analyzing format, color, font, alignment, and contextual information, to determine arrangement types and data types, allowing for automatic data organization and merging of data from multiple images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If OCR technology is used to process images of printed documents, then text recognition is automated, but accuracy deteriorates when text is arranged in complex arrangements

Engineering Contradiction:

Improveautomation of text recognitionVSAvoidtext recognition accuracy

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The patent segments the text recognition process into multiple stages: initial OCR processing, error detection through pattern recognition, and corrective processing. Complex text arrangements are identified and handled through specialized processing paths, separating them from standard OCR workflows to improve overall accuracy while maintaining automation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary processing steps between image input and final text output, including intermediate representation layers, contextual analysis modules, and validation mechanisms. These intermediaries help bridge the gap between automated OCR and accurate text recognition for complex arrangements.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If manual editing is performed to ensure correct text recognition, then accuracy is improved, but efficiency deteriorates

Engineering Contradiction:

Improvetext recognition accuracyVSAvoidprocessing efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent performs preliminary processing and validation steps automatically before manual intervention is needed. By pre-processing images, detecting potential errors, and preparing corrected versions, the system reduces the scope and time required for manual editing, thus improving efficiency while maintaining accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements self-correcting mechanisms that automatically fix common OCR errors without manual intervention. Through built-in validation, cross-referencing, and error correction algorithms, the system handles routine cases autonomously, reserving manual editing only for complex or ambiguous cases.

Inventive Principle:

Principle #25Self-service

3Reliability

If manual data entry is performed for complex text arrangements, then data accuracy is improved, but time consumption increases

Engineering Contradiction:

Improvedata accuracyVSAvoiddata entry time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent creates intermediate digital representations and copies of text data at various processing stages. These copies can be automatically validated, compared, and corrected before final data entry, reducing the need for time-consuming manual verification while maintaining data accuracy.

Inventive Principle:

Principle #26Copying

4Speed

If simple OCR processing is used, then processing speed is maintained, but adaptability to different text formats deteriorates

Engineering Contradiction:

Improveprocessing speedVSAvoidhandling of text arrangements

Core Design Contradiction:

SpeedVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic processing system that adapts its complexity based on the input characteristics. Simple texts undergo fast standard OCR processing, while complex arrangements automatically trigger more sophisticated processing paths. This dynamic adaptation maintains speed for simple cases while improving versatility for complex ones.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system is designed with universal processing capabilities that can handle multiple text formats and arrangements through a unified framework. By creating a multi-functional processing architecture, the system maintains adaptability across different text types without requiring separate specialized systems for each format.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9824269B2Enhanced interpretation of character arrangements

Publication Date: 2017.11.21 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Technologies are described herein for interpreting character arrangements. An image including an arrangement of characters may be received or captured by a computing device. Techniques described herein generate data representative of the characters. Characteristics and other information interpreted from the image may be processed to determine a data type. The data representative of the characters may be arranged into a data structure based on the data type, an arrangement type and/or other information interpreted from the image. The data type may indicate one or more attributes of the arranged data such as a format, font, date, language, or currency. The data type may also indicate how data is used in a process, equation or calculation. In addition, the data type may identify an anchor that may be used to merge data generated from the image with other data generated from another image.